检索结果-内蒙古大学图书馆

Robust Line-Convex Polygon Intersection Computation in E2 using Projective Space Representation

Machine Graphics and Vision 2023年第3-4期32卷 3-16页

作者： Skala, Vaclav Dept. of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic

This paper describes modified robust algorithms for a line clipping by a convex polygon in E2 and a convex polyhedron in E3. The proposed algorithm is based on the Cyrus-Beck algorithm and uses homogeneous coordinates to increase the robustness of computation. The algorithm enables computation fully in the projective space using the homogeneous coordinates and the line can be given in the projective space, in general. If the result can remain in projective space, no division operation is needed. It supports the use of vector-vector operations, SSE/AVX instructions, and GPU. © 2023 Institute of Information Technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Discrimination of Vibrotactile Stimuli: Effects of Frequency Variation

Discrimination of Vibrotactile Stimuli: Effects of Frequency...

引用

ASME 2023 International Mechanical engineering Congress and Exposition, IMECE 2023

作者： Yeganeh, Nashmin Makarov, Ivan Kristjánsson, Árni Unnthorsson, Runar The Faculty of Industrial Engineering Mechanical Engineering and Computer Science University of Iceland Reykjavik Iceland The Faculty of Industrial Engineering Mechanical Engineering and Computer Science The Faculty of Psychology University of Iceland Reykjavik Iceland The Faculty of Psychology University of Iceland Reykjavik Iceland

ISBN: (纸本)9780791887585

This paper reports on an empirical study that investigated the effect of frequency on the acuity of spatial localization on the skin of the forearm, as well as differences in localizability at different locations on the forearm. Three actuators were positioned in a 3 × 1 array along the forearm, and two adjacent actuators were sequentially activated with a 100 ms interstimulus interval, followed by activation of one of the three actuators in random order. Participants were asked about the direction of the second stimulation relative to the first one, and whether it was perceived in the same location as the first, below, or above it. Three frequencies — 100Hz, 200Hz, and 250Hz — were used for the stimuli. Results show that the frequency of the stimulus has a negligible influence on accuracy when the amplitude is kept constant. However, significant differences in the localization accuracy were found at different parts of the forearm. This study provides valuable insights into the design of tactile displays for conveying information on the skin. It suggests that spatial resolution may be optimized by positioning the actuators appropriately, rather than by manipulating the frequency of the stimulus. Copyright © 2023 by ASME.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

Improving Software Defects Detection: An In-Depth Analysis of Machine Learning Methods and Static Analysis Tools for Greater Accuracy 2

Improving Software Defects Detection: An In-Depth Analysis o...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Bobade, Veer Puri, Chetan DMIHER Faculty of Engineering And Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India DMIHER Faculty of Engineering And Technology Department of Computer Science and Engineering Maharashtra Wardha India

ISBN: (纸本)9798331505745

Enhancing software quality and reducing testing expenses requires better software fault detection. To guarantee the dependability and usability of software, Software Defect Prediction (SDP) uses machine learning approaches to anticipate and address any problems early in the development cycle. Numerous machine learning techniques, such as Support Vector Machines (SVM), Random Forest (RF), Logistic Regression, Naïve Bayes, Multilayer Perceptron (MLP), Decision Stump, J48, Lazy IBK, and ZeroR, are thoroughly examined in this work. With an emphasis on feature selection as a crucial step in increasing prediction accuracy and lower computing costs, these approaches are assessed for their capacity to detect software flaws precisely. This research study demonstrates how these models may improve fault identification and prevention procedures using historical records from sources such as the PROMISE repository. The study highlights the best practices for machine learning-based software quality assurance, lowering expenses while guaranteeing superior results. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

UNRAVELING THE EFFECTIVENESS OF THE K-NN ALGORITHM FOR IMBALANCED DATA IN RESEARCH TOPIC RECOMMENDATIONS

引用

Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University 2024年第1期59卷 271-282页

作者： Muludi, Kurnia Aisyah, Nonik Nama, Gigih Forda Lumbanraja, Favorisen R. Informatics & Business Institute Darmajaya Bandar Lampung35142 Indonesia Computer Science Department Faculty of Science The University of Lampung Bandar Lampung Indonesia Informatics Engineering Department Faculty of Science The University of Lampung Bandar Lampung Indonesia

This study addresses the challenge of selecting research topics for undergraduate students, focusing on computer science, by evaluating a recommendation model based on the k-Nearest Neighbor algorithm (kNN). The objective is to enhance the accuracy of research topic recommendations in the presence of imbalanced data. The methodology involves data cleaning, transformation, and correlation-based feature selection, with a particular focus on addressing missing values and optimizing the feature set. The Synthetic Minority Over-Sampling Technique (SMOTE) is employed to balance the dataset. The model development includes a comprehensive analysis of various k values, leading to the identification of k=3 with Manhattan distance as the optimal configuration, achieving an accuracy of 82%. The experiment explores different training data proportions, revealing that a 90:10 ratio yields the highest accuracy. This study incorporates a Grid Search technique for hyperparameter tuning, highlighting the importance of selecting appropriate distance metrics and nearest neighbor values. The system implementation is presented with user and administrator interfaces. Findings indicate varying model performance across research categories, emphasizing the need for category-specific evaluation metrics. The study concludes with a discussion on the significance of the results, which contribute to the improvement of research topic recommendation systems for students through the integration of advanced machine learning techniques. © 2024 by the authors.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Biometrics: A Novel Framework for Facial Recognition Interpretation

Explainable AI in Biometrics: A Novel Framework for Facial R...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Agrawal, Ansh Kaur, Kirandeep Kaur, Harkeerat Indian Institute of Technology Computer Science Engineering Jammu & Kashmir Jammu India Indian Institute of Technology Faculty Computer Science Engineering Jammu & Kashmir Jammu India

ISBN: (纸本)9798331533311

In recent years, the integration of Explainable Artificial Intelligence (XAI) in facial biometrics has gained momentum, driven by a growing need for transparency in automated decision-making systems. This paper explores the application of XAI in face detection and identification to bridge the gap between model accuracy and interpretability, aiming to address challenges unique to biometric systems, including bias mitigation, user trust, and ethical implications. Unlike traditional 'black-box' models, the proposed framework incorporates visual and feature-based explanations that highlight key facial regions contributing to identification outcomes, enabling more transparent model assessments. We evaluate the effectiveness of state-of-the-art XAI techniques, such as SHAP, LIME, and Grad-CAM, through rigorous testing on diverse datasets under varying conditions, including occlusions, lighting, and facial expressions. Additionally, this research introduces a novel hybrid interpretability metric tailored to biometric applications, assessing the quality of explanations based on fidelity, usability, and impact on user trust. Results demonstrate that the proposed XAI-enhanced model offers insights into decision processes without compromising accuracy, advancing the state of explainability in biometric systems. This work underscores the importance of explainability as a means to achieve ethical, reliable, and legally compliant AI systems in sensitive domains like facial biometrics. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Automated API Testing with Karate Framework: A Case Study of an Online Assessment Web Application 20

Automated API Testing with Karate Framework: A Case Study of...

引用

20th International Joint Conference on computer science and Software engineering, JCSSE 2023

作者： Gidvarowart, Supagid Suchato, Atiwong Wanvarie, Dittaya Pratanwanich, Naruemon Tuaycharoen, Nuengwong Chulalongkorn University Faculty of Engineering Department of Computer Engineering Bangkok Thailand Chulalongkorn University Faculty of Science Department of Mathematics and Computer Science Bangkok Thailand

ISBN: (纸本)9798350300505

This case study uses the Karate Framework to reduce the time and resources required for testing an application programming interface (API) for an Online Assessment Web Application, which is part of a continuous development process involving numerous complex features and test cases challenging to perform tests manually. The study aims to verify the correctness of the API's operation and facilitate regression testing during the development process to promptly detect errors. The study involved the testing of 162 test cases using the Karate Framework. Additionally, software quality assurance reports were created to confirm the quality and effectiveness of the Karate Framework in reducing manual testing time by over several hours compared with manual testing. Also, it is more effective than Robot Framework due to Karate Framework's capability of parallel threads. The findings suggest that using the Karate Framework can potentially optimize API testing processes of the case study. © 2023 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

New exact solutions of the Mikhailov-Novikov-Wang equation via three novel techniques

引用

Journal of Ocean engineering and science 2023年第1期8卷 103-110页

作者： Arzu Akbulut Melike Kaplan Mohammed K.A.Kaabar Mathematics-Computer Department Art-Science FacultyEski¸s ehir Osmangazi UniversityEski¸s ehirTurkey Department of Computer Engineering Engineering and Architecture FacultyKastamonu UniversityKastamonuTurkey Institute of Mathematical Sciences Faculty of ScienceUniversity of MalayaKuala Lumpur 50603Malaysia

The current work aims to present abundant families of the exact solutions of Mikhailov-Novikov-Wang equation via three different *** adopted methods are generalized Kudryashov method(GKM),exponential rational function method(ERFM),and modified extended tanh-function method(METFM).Some plots of some presented new solutions are represented to exhibit wave *** results in this work are essential to understand the physical meaning and behavior of the investigated equation that sheds light on the importance of investigating various nonlinear wave phenomena in ocean engineering and *** equation provides new insights to understand the relationship between the integrability and water waves’phenomena.

关键词： Exact solutions Generalized Kudryashov method Modified extended tanh-function method Symbolic computation PDEs

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Insights from Vast Data: An Overview of Deep Learning Techniques for Big Data 4

Exploring Deep Insights from Vast Data: An Overview of Deep ...

引用

4th International Conference on Electrical engineering and computer science, ICECOS 2024

作者： Baez Hasan, Sarhad Kareem, Shahab Wahhab Ameen, Didar Dlshad Hamad Soran University Faculty of Science Computer Science Department Soran Iraq Erbil Polytechnic University College of Engineering Knowledge University Department of Information System Engineering Department of Computer Engineering Erbil Iraq

ISBN: (纸本)9798350368253

Big data has emerged very fast, and this has brought both opportunities and problems that are related to the application of deep learning. This paper explores how deep learning can be implemented using big data and in particular the Apache Mahout library. Unlike most other machine learning tools, Mahout can perform distributed computation, especially while using the MapReduce frameworks including Apache Hadoop and Apache Spark. However, this study does not only focus on the explanation of the need for Mahout's integration and employment but also carries out a high-fidelity argument on how deep learning algorithms can be incorporated in the Mahout framework to optimize the manipulation of large and complicated datasets. Mahout-based contributions include the comparative analysis of key deep learning paradigms including distributed processing, parallel processing and transfer learning. This paper also includes examples of the Mahout deep learning integration use and its application in real contexts. This article describes the challenges that currently organizations face in handling big data and indeed, the potential threats these challenges pose to the success of deep learning techniques when used in organizations' big data processing and analysis. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Control Displaying of Web Push Notifications Inducing Users to Phishing Websites 7

Control Displaying of Web Push Notifications Inducing Users ...

引用

7th IEEE Conference on Dependable and Secure Computing, DSC 2024

作者： Sato, Masaya Mandai, Ryuki Okayama Prefectural University Faculty of Computer Science and Systems Engineering Soja Japan Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Japan

ISBN: (纸本)9798331540289

The number of phishing websites is increasing, and the methods used to direct users to these sites are becoming more diverse. As web push notifications become more widespread, adversaries have begun using them as a method to direct users to phishing websites, known as phishing web push notifications. While protection against other phishing methods has been widely studied, countermeasures against phishing web push notifications remain an ongoing research topic. In this paper, we explore a method to control the display of web push notifications to protect users from phishing attempts. To minimize the cost of implementing and introducing the control mechanism, we utilized a browser extension to manage the display of web push notifications. We employed a keyword-based approach to detect and prevent the display of suspicious web push notifications. Our experimental results demonstrated that the proposed method effectively blocks phishing notifications. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Investigation of DNA discontinuity for detecting tuberculosis

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1149-1163页

作者： Nimmy, Sonia Farhana Sarowar, Md. Golam Dey, Nilanjan Ashour, Amira S. Santosh, K.C. Department of Computer Science and Engineering Notre Dame University Dhaka Bangladesh Department of Computer Science and Engineering East West University Dhaka Bangladesh Department of Information Technology Techno India College of Technology Kolkata India Department of Electronics and Electrical Communications Engineering Faculty of Engineering Tanta University Tanta Egypt Vermillion United States

Discontinuity in long Deoxyribonucleic Acid (DNA) sequences creates harmful diseases. Changes in the DNA structure refers to changes in the human immunity system. Tuberculosis is a critical disease that causes coughing, fatigue, unintentional weight loss and fever on aged people due to the disorder in the DNA. Breaks or mutations over long DNA sequences are the pivotal reasons for this fatal disease. This study developed an automated machine learning technique to assess the total number of such breaks in the long DNA sequences. Data cleansing and deep neural network techniques are applied to handle this big data. The National Center for Biotechnology Information (NCBI) database has been used to extract the amino acid sequences for Tuberculosis disease from the big DNA datasets. Results reveal that the proposed automated approach is significantly effective for the determination of DNA sequence breaks for the tuberculosis diseases due to the high sensitivity of Markov chain as well as the effective normalization techniques. This approach fixed the size of the training datasets and recursively divide the whole dataset into certain length. The study also adopts multiple predictions approaches, such as the hidden Markov chain, Box-Cox transformation and linear transformation to forecast about the breaks for any long positions of the training and testing datasets. The results demonstrated that hidden the Markov chain model provided faster analysis with more accurate and reliable results. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：